© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 3437
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs signaling negation or lack of action

    oai_token-act-pair · gpt-3.5-turbo

    auxiliary verbs and modal verbs indicating actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arez
    -0.77
    ovember
    -0.76
    inosaur
    -0.74
    orea
    -0.70
    opian
    -0.69
    onomy
    -0.69
    ixties
    -0.68
    hig
    -0.65
    trap
    -0.64
    uran
    -0.64
    POSITIVE LOGITS
     they
    1.01
     there
    0.90
     it
    0.85
     he
    0.82
     we
    0.81
     she
    0.73
     anyone
    0.73
    they
    0.64
     THEY
    0.63
     commentators
    0.61
    Activations Density 0.076%

    No Known Activations